hugpadhugpad

cerebras / GLM-4.6-REAP-268B-A32B-FP8

Text Generation269B11712Updated Oct 23, 2025
Hugging Face

Downloads

117

Likes

12

Last updated

Oct 23, 2025

License

mit

Introducing GLM-4.6-REAP-268B-A32B-FP8, a memory-efficient compressed variant of GLM-4.6-FP8 that maintains near-identical performance while being 25% lighter.

Tasks & library

  • text generation
  • transformers

Tags

  • transformers
  • glm4_moe
  • text-generation
  • glm
  • MOE
  • pruning

Technical specifications

Parameters269B
Librarytransformers
Languagesen
Base modelzai-org/GLM-4.6-FP8
Licensemit